Should artificial neural networks replace linear models in tree ring based climate reconstructions?

2016 ◽  
Vol 40 ◽  
pp. 102-109 ◽  
Author(s):  
Jernej Jevšenak ◽  
Tom Levanič
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Tree Ring ◽  
Linear Models ◽  
Climate Reconstructions ◽  
Artificial Neural

scholarly journals Forecasting Albanian Time Series with Linear and Nonlinear Univariate Models

2021 ◽  
Vol 10 (5) ◽  
pp. 293
Author(s):  
Blerina Vika ◽  
Ilir Vika
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Linear Models ◽  
Smooth Transition ◽  
Parameter Method ◽  
Economic Time Series ◽  
Nonlinear Methods ◽  
Linear And Nonlinear ◽  
Artificial Neural

Albanian economic time series show irregular patterns since the 1990s that may affect economic analyses with linear methods. The purpose of this study is to assess the ability of nonlinear methods in producing forecasts that could improve upon univariate linear models. The latter are represented by the classic autoregressive (AR) technique, which is regularly used as a benchmark in forecasting. The nonlinear family is represented by two methods, i) the logistic smooth transition autoregressive (LSTAR) model as a special form of the time-varying parameter method, and ii) the nonparametric artificial neural networks (ANN) that mimic the brain’s problem solving process. Our analysis focuses on four basic economic indicators – the CPI prices, GDP, the T-bill interest rate and the lek exchange rate – that are commonly used in various macroeconomic models. Comparing the forecast ability of the models in 1, 4 and 8 quarters ahead, we find that nonlinear methods rank on the top for more than 75 percent of the out-of-sample forecasts, led by the feed-forward artificial neural networks. Although the loss differential between linear and nonlinear model forecasts is often found not statistically significant by the Diebold-Mariano test, our results suggest that it can be worth trying various alternatives beyond the linear estimation framework.   Received: 19 June 2021 / Accepted: 25 August 2021 / Published: 5 September 2021

scholarly journals Subjective Air Traffic Complexity Estimation Using Artificial Neural Networks

2019 ◽  
Vol 31 (4) ◽  
pp. 377-386 ◽  
Author(s):  
Petar Andraši ◽  
Tomislav Radišić ◽  
Doris Novak ◽  
Biljana Juričić
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Linear Models ◽  
Air Traffic ◽  
Traffic Situation ◽  
Network Configuration ◽  
Air Traffic Controllers ◽  
Complexity Estimation ◽  
Artificial Neural

Air traffic complexity is usually defined as difficulty of monitoring and managing a specific air traffic situation. Since it is a psychological construct, best measure of complexity is that given by air traffic controllers. However, there is a need to make a method for complexity estimation which can be used without constant controller input. So far, mostly linear models were used. Here, the possibility of using artificial neural networks for complexity estimation is explored. Genetic algorithm has been used to search for the best artificial neural network configuration. The conclusion is that the artificial neural networks perform as well as linear models and that the remaining error in complexity estimation can only be explained as inter-rater or intra-rater unreliability. One advantage of artificial neural networks in comparison to linear models is that the data do not have to be filtered based on the concept of operations (conventional vs. trajectory-based).

scholarly journals ASSESSING ALTERNATIVES TO ESTIMATE THE STEM VOLUME OF A SEASONAL SEMI-DECIDUOUS FOREST

FLORESTA ◽  
2017 ◽  
Vol 47 (4) ◽  
pp. 375
Author(s):  
Jadson Coelho De Abreu ◽  
Carlos Pedro Boechat Soares ◽  
Helio Garcia Leite
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Support Vector Machines ◽  
Linear Models ◽  
Deciduous Forest ◽  
Stem Volume ◽  
Categorical Variables ◽  
Support Vector ◽  
Vector Machines ◽  
Artificial Neural

AbstractThe objective of this study was to evaluate the use of linear and hybrid linear models, artificial neural networks (ANN) and support vector machine (SVM) in the estimation of the stem volume in a Seasonal Semi-deciduous Forest. Cubing data of 99 sample-trees of 15 species were used for this purpose. After analysis, we verified that the inclusion of the species as random effect did not contribute to increase the accuracy of the estimates in the structure of a hybrid model. Artificial neural networks and support vector machines, including species as input categorical variables, were the best alternatives to estimate the stem volume of trees of the Seasonal Semi-deciduous Forest.Keywords: Stem volume; artificial neural networks; support vector machines; hybrid linear models; uneven-aged forest. ResumoAvaliando alternativas para estimar o volume do fuste de uma Floresta Estacional Semidecidual. O objetivo desse estudo foi   avaliar o uso de modelos lineares e lineares mistos, redes neurais   artificiais (RNA) e máquina de vetor de suporte (MVS) na estimação dos   volumes dos fustes de árvores em uma Floresta Estacional Semidecidual. Dados de cubagem de 99 árvores-amostra   de 15 espécies foram utilizados para esta finalidade. Após análises, verificou-se que   a inclusão das espécies como efeito aleatório não contribuiu para aumentar a   exatidão das estimativas na estrutura de um modelo misto. As redes neurais artificiais e   as máquinas de vetores de suporte, incluindo as espécies como variáveis   categóricas de entrada, foram as melhores alternativas para estimar o volume   dos fustes das árvores da Floresta Estacional Semidecidual.Palavras-chaves: Volume do   fuste; redes neurais artificiais; máquinas de vetor de suporte; modelos   lineares mistos; floresta inequiânea. 

Sign in / Sign up

Export Citation Format

Share Document